An effective support vector data description with relevant metric learning

Authors:
Zhe Wang;Daqi Gao;Zhisong Pan
Affiliations:
Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, P.R China;Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, P.R China;Institute of Command Automation, PLA University of Science & Technology, Nanjing, P.R China
Venue:
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
Year:
2010

Citing 6
Cited 0

Matrix computations (3rd ed.)

Matrix computations (3rd ed.)
Support vector domain description

Pattern Recognition Letters - Special issue on pattern recognition in practice VI
Adjustment Learning and Relevant Component Analysis

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Support Vector Data Description

Machine Learning
Estimating the Support of a High-Dimensional Distribution

Neural Computation
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Support Vector Data Description (SVDD) as a one-class classifier was developed to construct the minimum hypersphere that encloses all the data of the target class in a high dimensional feature space However, SVDD treats the features of all data equivalently in constructing the minimum hypersphere since it adopts Euclidean distance metric and lacks the incorporation of prior knowledge In this paper, we propose an improved SVDD through introducing relevant metric learning The presented method named RSVDD here assigns large weights to the relevant features and tights the similar data through incorporating the positive equivalence information in a natural way In practice, we introduce relevant metric learning into the original SVDD model with the covariance matrices of the positive equivalence data The experimental results on both synthetic and real data sets show that the proposed method can bring more accurate description for all the tested target cases than the conventional SVDD.